VisDrone aerial object detection toolkit with 33 models (Torchvision + YOLO), training, evaluation, video inference, benchmarking, and annotation conversion.
Many yolov8 model are trained on the VisDrone dataset.
Lamaah: A YOLO-Based Model for Multi-Scale Object Detection in UAV Systems
Object detection format converter from VisDrone2019-DET to Yolo.
object detection using YOLO11x on VisDrone dataset
FOLT-inspired motion-aware multi-object tracking for UAV video using YOLOX and FastFlowNet.
Attention-guided object detection on VisDrone using Grad-CAM++ and YOLO, with metrics and visual outputs.
An end-to-end edge computer vision pipeline running real-time YOLOv8 aerial object detection on aerial drone footage optimized on CoreML & Neural Engine. Includes multi-runtime benchmarking, CLI inference, and automated testing.
To associate your repository with the visdrone-dataset topic, visit your repo's landing page and select "manage topics."